mcpbeat Sign in

AI Compute Radar MCP Server

by aicomputeradar Your server? Claim it
answering

AI Compute Radar is answering right now. Last checked 10 min ago. 58 installs a week from npm. It exposes 6 tools.

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

Installs per day peak 318 · avg 13
a month agotoday
Uptime history 51 days of history · worst day 97%
51 days agonow
100.0%
Uptime 24h
91 of 91 checks
6
Tools
read from the server
179 ms
Response time
average over 24h
58
Installs / week
npm and PyPI

What changed 9

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 September 2026. No other catalogue keeps this.

29 Oct a tool changed the parameters it asks for price_history
27 Oct a tool appeared price_history
27 Oct a tool changed version
24 Oct a tool changed version
22 Oct a tool changed version
5 Oct a tool description was rewritten gpu_prices
2 Oct a tool description was rewritten gpu_prices
24 Sep a tool description was rewritten gpu_prices
21 Sep a tool description was rewritten gpu_prices

AI Compute Radar missed 3 checks this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add ai-compute-radar --transport http https://aicomputeradar.dev/api/mcp
Settings → Connectors → Add custom connector, then paste this address
https://aicomputeradar.dev/api/mcp
~/.codex/config.toml
[mcp_servers.ai-compute-radar]
url = "https://aicomputeradar.dev/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "ai-compute-radar": {
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "ai-compute-radar": {
      "type": "http",
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

fit
find_fit
Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.
gpu
gpu_prices
Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week collected, a trend word, and the days excluded as marketplace glitches, plus RunPod's lowest posted on-demand price per class (a list price, not a median), Clore.ai's median for the same class (a second marketplace, never blended), and the AWS, Azure and Oracle Cloud pay-as-you-go list prices per GPU-hour, each with the instance type, VM size or bare-metal shape the price sits in (list prices, read four times a day, no statement about capacity). The index describes what prices did; it never forecasts.
hardware
list_hardware
Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.
price
price_history
Daily price history per GPU class and source, up to 90 days: the rows the Rent Index and the 30-day range are computed from. Marketplace days (Vast.ai, Clore.ai) are medians over the day's counted hourly medians with min, p75 and offer count; list-price days (RunPod, AWS, Azure, Oracle Cloud, Lambda, Nebius, CoreWeave, Hyperstack) carry the posted price. Each row says which kind it is; never blend the two. Describes what prices did; it never forecasts.
trending
trending_models
Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.
weekly
weekly_pick
The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a device-by-device fit ladder and the written report including its caveats. Pass week (e.g. 2026-w37) for a past issue. issue is null until the first issue is published.

Endpoints

URLTransportStateLatencyChecked
https://aicomputeradar.dev/api/mcp streamable-http answering 101 ms 10 min ago

Alternatives to AI Compute Radar

same job, measured the same way
Model Tested
by modeltested

Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.

5 tools answering
Local AI Prices
by localaiprices

Daily prices, stock and measured LLM speeds for local AI computers and graphics cards.

5 tools answering
Local AI Picks
by localaipicks

Find open-weight AI models that fit your hardware, with weight sizes, memory and sources.

4 tools answering
SpareHive GPU Advisor
by richardxu001

Read-only GPU advisor: model VRAM needs, fit checks and rental prices, with evidence grades.

5 tools answering
Compute Finance Oracle
by compute-finance

Live AI compute pricing oracle — real-time LLM model prices across providers

222 installs/wk local only
LLM Configurator
by aikuba

Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.

5 tools answering
ToolDrift MCP
by thecompound

ToolDrift: Current AI model pricing and which models coding tools route to.

local only
readygpu: hardware for local AI
by readygpu

Live UK, Germany, Canada and US prices for GPUs and Macs that run open AI models. No sign-up.

6 tools answering

AI Compute Radar — questions

Answers built from our own checks of this server.

What can AI Compute Radar do?
It exposes 6 tools, read directly from the server on our last check. Among them: find_fit, gpu_prices, list_hardware, price_history, trending_models, weekly_pick. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is AI Compute Radar working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 179 ms. The bar chart above shows every period we have measured.
How do I connect AI Compute Radar?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AI Compute Radar need an API key?
No. AI Compute Radar completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AI Compute Radar?
It answers our handshake in 179 ms on average, which is faster than 75% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use AI Compute Radar?
The npm package ai-compute-radar was installed 58 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.